English
Related papers

Related papers: Shorter Thoughts, Same Answers: Difficulty-Scaled …

200 papers

Recent advances in large language models (LLMs) have introduced latent reasoning as a promising alternative to autoregressive reasoning. By performing internal computation with hidden states from previous steps, latent reasoning benefit…

Computation and Language · Computer Science 2025-10-24 Zhenrui Yue , Bowen Jin , Huimin Zeng , Honglei Zhuang , Zhen Qin , Jinsung Yoon , Lanyu Shang , Jiawei Han , Dong Wang

While large reasoning models demonstrate strong performance on complex tasks, they lack the ability to adjust reasoning token usage based on task difficulty. This often leads to the "overthinking" problem -- excessive and unnecessary…

Computation and Language · Computer Science 2025-10-14 Siye Wu , Jian Xie , Yikai Zhang , Aili Chen , Kai Zhang , Yu Su , Yanghua Xiao

While long, explicit chains-of-thought (CoT) have proven effective on complex reasoning tasks, they are costly to generate during inference. Non-verbal reasoning methods have emerged with shorter generation lengths by leveraging continuous…

Computation and Language · Computer Science 2026-04-28 Keshav Ramji , Tahira Naseem , Ramón Fernandez Astudillo

Large Language Models (LLMs) achieve superior performance through Chain-of-Thought (CoT) reasoning, but these token-level reasoning chains are computationally expensive and inefficient. In this paper, we introduce Compressed Latent…

Computation and Language · Computer Science 2026-02-04 Wenhui Tan , Jiaze Li , Jianzhong Ju , Zhenbo Luo , Ruihua Song , Jian Luan

Enhancing the reasoning capabilities of large language models effectively using reinforcement learning (RL) remains a crucial challenge. Existing approaches primarily adopt two contrasting advantage estimation granularities: token-level…

Machine Learning · Computer Science 2025-10-22 Yiran Guo , Lijie Xu , Jie Liu , Dan Ye , Shuang Qiu

Recent advances in large language models (LLMs) highlight the importance of post training techniques for improving reasoning and mathematical ability. Group Relative Policy Optimization (GRPO) has shown promise in this domain by combining…

Machine Learning · Computer Science 2026-03-20 Gabriele Carrino , Andrea Sassella , Nicolo Brunello , Federico Toschi , Mark James Carman

Small Vision Language Models (SVLMs) generally refer to models with parameter sizes less than or equal to 2B. Their low cost and power consumption characteristics confer high commercial value. However, their reasoning abilities are limited…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Fanyi Wang , Binzhi Dong , Haotian Hu , Jinjin Xu , Zhiwang Zhang

Test-Time Scaling (TTS) refers to approaches that improve reasoning performance by allocating extra computation during inference, without altering the model's parameters. While existing TTS methods operate in a discrete token space by…

Computation and Language · Computer Science 2025-05-28 Yige Xu , Xu Guo , Zhiwei Zeng , Chunyan Miao

Although chain-of-thought reasoning and reinforcement learning (RL) have driven breakthroughs in NLP, their integration into generative vision models remains underexplored. We introduce ReasonGen-R1, a two-stage framework that first imbues…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Yu Zhang , Yunqi Li , Yifan Yang , Rui Wang , Yuqing Yang , Dai Qi , Jianmin Bao , Dongdong Chen , Chong Luo , Lili Qiu

Chain-of-thought (CoT) reasoning enables large language models (LLMs) to break down complex problems into interpretable intermediate steps, significantly enhancing model transparency and performance in reasoning tasks. However, conventional…

Machine Learning · Computer Science 2026-01-30 Junda Wu , Yuxin Xiong , Xintong Li , Sheldon Yu , Zhengmian Hu , Tong Yu , Rui Wang , Xiang Chen , Jingbo Shang , Julian McAuley

Chain-of-thought (CoT) distillation aims to enhance small language models' (SLMs) reasoning by transferring multi-step reasoning capability from the larger teacher models. However, existing work underestimates rationale quality, focusing…

Computation and Language · Computer Science 2025-09-30 Jianzhi Yan , Le Liu , Youcheng Pan , Shiwei Chen , Yang Xiang , Buzhou Tang

Long chain-of-thought (CoT) reasoning improves large vision--language models, but visual information often fades during generation, limiting long-horizon multimodal reasoning. Existing methods either re-inject vision at inference or train…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Xuan Gong , Hanbo Huang , Hao Zheng , Yiran Zhang , Wenbin Dai , Weishu Zhao , Shiyu Liang

A key paradigm to improve the reasoning capabilities of large language models (LLMs) is to allocate more inference-time compute to search against a verifier or reward model. This process can then be utilized to refine the pretrained model…

Artificial Intelligence · Computer Science 2025-03-04 Juno Kim , Denny Wu , Jason Lee , Taiji Suzuki

Multimodal reasoning models (MRMs) trained with reinforcement learning with verifiable rewards (RLVR) show improved accuracy on visual reasoning benchmarks. However, we observe that accuracy gains often come at the cost of reasoning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Sai Srinivas Kancheti , Aditya Kanade , Rohit Sinha , Vineeth N Balasubramanian , Tanuja Ganu

Recent studies have shown that making a model spend more time thinking through longer Chain of Thoughts (CoTs) enables it to gain significant improvements in complex reasoning tasks. While current researches continue to explore the benefits…

Computation and Language · Computer Science 2025-10-14 Wenkai Yang , Shuming Ma , Yankai Lin , Furu Wei

Large language models (LLMs) have shown impressive capabilities in handling complex tasks through long-chain reasoning. However, the extensive reasoning steps involved can significantly increase computational costs, posing challenges for…

Computation and Language · Computer Science 2025-05-28 Yunhao Wang , Yuhao Zhang , Tinghao Yu , Can Xu , Feng Zhang , Fengzong Lian

Chain-of-thought (CoT) reasoning is useful for monitoring language models only when the reasoning trace faithfully reflects the computation that produces the final answer. However, models can rely on prompt-to-answer shortcuts that bypass…

Machine Learning · Computer Science 2026-05-26 Jinghan Jia , Joe Benton , Eric Easley

On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once discovered and ceasing exploration of alternative strategies. We…

Artificial Intelligence · Computer Science 2026-05-20 Xiaozhe Li , Yang Li , Xinyu Fang , Shengyuan Ding , Peiji Li , Yongkang Chen , Yichuan Ma , Tianyi Lyu , Linyang Li , Dahua Lin , Qipeng Guo , Qingwen Liu , Kai Chen

Large reasoning models (LRMs) exhibit diverse high-level reasoning patterns (e.g., direct solution, reflection-and-verification, and exploring multiple solutions), yet prevailing training recipes implicitly bias models toward a limited set…

Artificial Intelligence · Computer Science 2026-01-13 Hanbin Wang , Jingwei Song , Jinpeng Li , Fei Mi , Lifeng Shang

Image captioning tasks usually use two-stage training to complete model optimization. The first stage uses cross-entropy as the loss function for optimization, and the second stage uses self-critical sequence training (SCST) for…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Xu Liang